Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection

Deepfake technology poses significant threats in various domains, including politics, cybersecurity, and social media. This study uses the golden frame selection technique to present a neural network ensemble method for deepfake classification. The proposed approach optimizes computational resources...

Full description

Saved in:
Bibliographic Details
Main Authors: Khrystyna Lipianina-Honcharenko, Nazar Melnyk, Andriy Ivasechko, Mykola Telka, Oleg Illiashenko
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Big Data and Cognitive Computing
Subjects:
Online Access:https://www.mdpi.com/2504-2289/9/4/109
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144618300047360
author Khrystyna Lipianina-Honcharenko
Nazar Melnyk
Andriy Ivasechko
Mykola Telka
Oleg Illiashenko
author_facet Khrystyna Lipianina-Honcharenko
Nazar Melnyk
Andriy Ivasechko
Mykola Telka
Oleg Illiashenko
author_sort Khrystyna Lipianina-Honcharenko
collection DOAJ
description Deepfake technology poses significant threats in various domains, including politics, cybersecurity, and social media. This study uses the golden frame selection technique to present a neural network ensemble method for deepfake classification. The proposed approach optimizes computational resources by extracting the most informative video frames, improving detection accuracy. We integrate multiple deep learning models, including ResNet50, EfficientNetB0, Xception, InceptionV3, and Facenet, with an XGBoost meta-model for enhanced classification performance. Experimental results demonstrate a 91% accuracy rate, outperforming traditional deepfake detection models. Additionally, feature importance analysis using Grad-CAM highlights how different architectures focus on distinct facial regions, enhancing overall model interpretability. The findings contribute to of robust and efficient deepfake detection techniques, with potential applications in digital forensics, media verification, and cybersecurity.
format Article
id doaj-art-3ad9b9b53b5d4ddba663d3e31028274a
institution OA Journals
issn 2504-2289
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Big Data and Cognitive Computing
spelling doaj-art-3ad9b9b53b5d4ddba663d3e31028274a2025-08-20T02:28:19ZengMDPI AGBig Data and Cognitive Computing2504-22892025-04-019410910.3390/bdcc9040109Neural Network Ensemble Method for Deepfake Classification Using Golden Frame SelectionKhrystyna Lipianina-Honcharenko0Nazar Melnyk1Andriy Ivasechko2Mykola Telka3Oleg Illiashenko4Department of Information and Computing Systems and Control, Faculty of Computer Information Technologies, West Ukrainian National University, 46000 Ternopil, UkraineDepartment of Information and Computing Systems and Control, Faculty of Computer Information Technologies, West Ukrainian National University, 46000 Ternopil, UkraineDepartment of Information and Computing Systems and Control, Faculty of Computer Information Technologies, West Ukrainian National University, 46000 Ternopil, UkraineDepartment of Information and Computing Systems and Control, Faculty of Computer Information Technologies, West Ukrainian National University, 46000 Ternopil, UkraineDepartment of Computer Systems, Networks and Cybersecurity, Faculty of Radio Electronics, Computer Systems and Infocommunications, National Aerospace University “KhAI”, 61000 Kharkiv, UkraineDeepfake technology poses significant threats in various domains, including politics, cybersecurity, and social media. This study uses the golden frame selection technique to present a neural network ensemble method for deepfake classification. The proposed approach optimizes computational resources by extracting the most informative video frames, improving detection accuracy. We integrate multiple deep learning models, including ResNet50, EfficientNetB0, Xception, InceptionV3, and Facenet, with an XGBoost meta-model for enhanced classification performance. Experimental results demonstrate a 91% accuracy rate, outperforming traditional deepfake detection models. Additionally, feature importance analysis using Grad-CAM highlights how different architectures focus on distinct facial regions, enhancing overall model interpretability. The findings contribute to of robust and efficient deepfake detection techniques, with potential applications in digital forensics, media verification, and cybersecurity.https://www.mdpi.com/2504-2289/9/4/109deepfake detectionneural network ensemblegolden frame selectionResNet50EfficientNetB0Xception
spellingShingle Khrystyna Lipianina-Honcharenko
Nazar Melnyk
Andriy Ivasechko
Mykola Telka
Oleg Illiashenko
Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection
Big Data and Cognitive Computing
deepfake detection
neural network ensemble
golden frame selection
ResNet50
EfficientNetB0
Xception
title Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection
title_full Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection
title_fullStr Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection
title_full_unstemmed Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection
title_short Neural Network Ensemble Method for Deepfake Classification Using Golden Frame Selection
title_sort neural network ensemble method for deepfake classification using golden frame selection
topic deepfake detection
neural network ensemble
golden frame selection
ResNet50
EfficientNetB0
Xception
url https://www.mdpi.com/2504-2289/9/4/109
work_keys_str_mv AT khrystynalipianinahoncharenko neuralnetworkensemblemethodfordeepfakeclassificationusinggoldenframeselection
AT nazarmelnyk neuralnetworkensemblemethodfordeepfakeclassificationusinggoldenframeselection
AT andriyivasechko neuralnetworkensemblemethodfordeepfakeclassificationusinggoldenframeselection
AT mykolatelka neuralnetworkensemblemethodfordeepfakeclassificationusinggoldenframeselection
AT olegilliashenko neuralnetworkensemblemethodfordeepfakeclassificationusinggoldenframeselection